| --- |
| pipeline_tag: text-to-image |
| --- |
| # Work in progress |
|
|
|
|
| The model files are almost identical to our t5sdxl-v0-bf16 model. |
| However it has had its model_config.json adjusted, so that it will work with |
| new code, that will be going into the "community" diffusers pipeline area. |
| |
| Alternatively, there is now a "demo.py" script that can use diffusers pipeline styles relatively cleanly, AS-IS! |
| |
| # Precision |
| Note that the unet is, sadly, only bf16 at this time, since we only have 4090s |
| |
| # Usage |
| |
| You can use it with the sample code in [demo.py](demo.py) |
| |
| |
| # Forward notes |
| |
| Hmm.. in retrospect... perhaps it would be better to use chatpig/t5-v1_1-xl-encoder-gguf instead of the xxl version. |
|
|
| That is natively 2048 dim, so no need for a projection layer. |
